Towards tailoring non-invasive brain stimulation using real-time fMRI and Bayesian optimization

TL;DR

This paper explores combining real-time fMRI with Bayesian optimization to personalize non-invasive brain stimulation protocols, aiming to enhance efficacy by tailoring stimulation to individual brain responses.

Contribution

It introduces a framework integrating real-time fMRI and Bayesian optimization for subject-specific tACS protocol identification, and evaluates kernel and acquisition function choices using empirical and simulation data.

Findings

Squared exponential kernel performs best for the Bayesian model.

Upper confidence bound acquisition function guides optimal search.

Framework sets foundation for real-time personalized brain stimulation experiments.

Abstract

Non-invasive brain stimulation, such as transcranial alternating current stimulation (tACS) provides a powerful tool to directly modulate brain oscillations that mediate complex cognitive processes. While the body of evidence about the effect of tACS on behavioral and cognitive performance is constantly growing, those studies fail to address the importance of subject- specific stimulation protocols. With this study here, we set the foundation to combine tACS with a recently presented framework that utilizes real-time fRMI and Bayesian optimization in order to identify the most optimal tACS protocol for a given individual. While Bayesian optimization is particularly relevant to such a scenario, its success depends on two fundamental choices: the choice of covariance kernel for the Gaussian process prior as well as the choice of acquisition function that guides the search. Using empirical (functional neuroimaging) as well as simulation data, we identified the squared exponential kernel and the upper confidence bound acquisition function to work best for our problem. These results will be used to inform our upcoming real- time experiments.